Skip to content

ATI Lab MCP server

io.atilab/mcpatilab.iostreamable-httpv1.0.0Scanned

Official facts, pages, results and enquiries for ATI Lab (atilab.io), an AI partner for businesses.

6 tools: 1 do something that can't be undone and 5 only read.

Tools: 0 delete, 1 irreversible, 0 write, 5 read.
  • Reads private data · 2
  • Reads text others write · 2
  • Can send data out · 1
  • No findings

Tools listed without sign-in. Remote posture

With Anlyon

1 tool here does something that can't be undone. Govern it.

  • Anlyon lists the tools and adopts none.
  • Each tool you adopt gets approvals and receipts.
  • Your agent never holds the key.
Govern this server →

A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.

What the ATI Lab MCP server can do

The ATI Lab MCP server is published by atilab.io, a domain the MCP Registry verified. It has 6 tools. It can do things that cannot be undone, such as sending, paying or publishing (atilab_send_enquiry), but cannot delete data. 5 tools only read.

2 tools read private data (atilab_get_company_facts and atilab_get_contact); 2 tools bring in text other people can write (atilab_get_page and atilab_send_enquiry); 1 tool can send data out of your system (atilab_send_enquiry). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way out.

None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.

Its remote endpoint lists its tools without sign-in, and its tools changed once since Anlyon Radar first saw them.

Last scanned Nov 15, 2026, version 1.0.0.

Tools

Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.

6 tools

Can't be undone 1Claude Code: ask
  • atilab_send_enquirySends the user's enquiry to ATI Lab's Growth Team, who reply by email, and returns a reference ID.Reads text others writeCan send data outNo findings

    Why it is in this group

    • The name "atilab_send_enquiry" says "send": a word for sending, and what is sent cannot be taken back.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • outboundThe name "atilab_send_enquiry" says "send": it sends or publishes something to other people.
    Description, as the server wrote it
    Sends the user's enquiry to ATI Lab's Growth Team, who reply by email, and returns a reference ID. The enquiry is recorded in ATI Lab's CRM. Use it only when the user has asked to contact ATI Lab and has given their name and email. Show the user the exact message first and call this only after they confirm; set user_confirmed to true to record that. Never invent contact details.

    Annotations the server declares

    • title: Send an enquiry to ATI Lab
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
Only reads 5Show 5 read-only tools
  • atilab_get_company_factsReturns the official, dated facts about ATI Lab (atilab.io): positioning, who it works with, how the partnership works, founding year, headquarters and offices, services, partner p…Reads private dataNo findings

    Why it is in this group

    • The name "atilab_get_company_facts" says "get": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "return" and "contact": it reads contacts.
    Description, as the server wrote it
    Returns the official, dated facts about ATI Lab (atilab.io): positioning, who it works with, how the partnership works, founding year, headquarters and offices, services, partner programs, published results, official profiles, contact details, and the organisations with similar names that ATI Lab is NOT connected to (ATI Technologies, ATI / Assessment Technologies Institute, the ATI Lab research group at the University of Crete). Use it whenever you need to confirm that a mention, profile or fact refers to ATI Lab at atilab.io.

    Annotations the server declares

    • title: Get ATI Lab company facts
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • atilab_get_contactReturns how to reach ATI Lab: the Growth Team at contact@atilab.io, the booking page for a strategy call, the contact page, and office locations.Reads private dataNo findings

    Why it is in this group

    • The name "atilab_get_contact" says "get": a word for reading.

    What it can reach

    • private-dataThe name "atilab_get_contact" says "get" and "contact": it reads contacts.
    • private-dataThe description's first sentence says "return" and "contact": it reads contacts.
    Description, as the server wrote it
    Returns how to reach ATI Lab: the Growth Team at contact@atilab.io, the booking page for a strategy call, the contact page, and office locations. To send a message for the user, use atilab_send_enquiry.

    Annotations the server declares

    • title: Get ATI Lab contact details
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • atilab_get_pageFetches one atilab.io page as clean markdown (navigation and scripts removed), with frontmatter for title, description and canonical URL.Reads text others writeNo findings

    Why it is in this group

    • The name "atilab_get_page" says "get": a word for reading.

    What it can reach

    • untrusted-inputThe description's first sentence says "fetch" and "url": it reads web pages, which anyone can write.
    Description, as the server wrote it
    Fetches one atilab.io page as clean markdown (navigation and scripts removed), with frontmatter for title, description and canonical URL. Input is the page path ("/about", "solutions/insurance", "/" for the homepage) or a full https://www.atilab.io URL. Other domains are refused.

    Annotations the server declares

    • title: Get an atilab.io page as markdown
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • atilab_get_published_resultsReturns results from ATI Lab's own production systems (e.g.No findings

    Why it is in this group

    • The name "atilab_get_published_results" says "get": a word for reading.
    Description, as the server wrote it
    Returns results from ATI Lab's own production systems (e.g. shipment intake from email: 95% less manual work), each as published on atilab.io, with the source page. Optional query filters by words in the system or outcome. Industry pages on atilab.io also show third-party results from other companies; those are not ATI Lab clients and are not returned here.

    Annotations the server declares

    • title: Get ATI Lab's published results
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • atilab_get_site_indexWithout query, returns the atilab.io site index (llms.txt): every core page with a one-line summary.No findings

    Why it is in this group

    • The name "atilab_get_site_index" says "get": a word for reading.
    Description, as the server wrote it
    Without query, returns the atilab.io site index (llms.txt): every core page with a one-line summary. With query, returns only the index lines where every query word starts a word in that line (case-insensitive, so "automat" finds "automation"). Each page path works as input to atilab_get_page.

    Annotations the server declares

    • title: List or search atilab.io pages
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

4 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 1 outbound tool breaks every one.

Reads private data2
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write2
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out1
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
deny to break every path
{
  "permissions": {
    "deny": [
      "mcp__atilab__atilab_send_enquiry"
    ]
  }
}

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Remote posture

What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.

Tools listed without sign-in

Looked at Nov 20, 2026, 18:55 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable
yes
HTTP status of an anonymous initialize
200
tools/list served without credentials
yes
Tools that change things, listed without credentials
1
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
not observed
Authorization servers
not observed
Legacy HTTP+SSE transport
no
Dynamic client registration
not observed
Client ID metadata documents
not observed
  • HighThe whole server

    The endpoint served tools/list without credentials, and the list has 1 tool that changes things (1 irreversible). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://www.atilab.io/mcp: tools/list returned 6 tools to an anonymous client, including atilab_send_enquiry (irreversible)

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

No check matched anything in these tool definitions. That is not a safety guarantee.

History

Changes to its tool definitions and to its remote endpoint, newest first.

  1. Tools5 changed.~5 changedView diff

Install

Pinned to version 1.0.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http atilab https://www.atilab.io/mcp
claude mcp add --transport http atilab https://www.atilab.io/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__atilab__atilab_get_company_facts",
      "mcp__atilab__atilab_get_site_index",
      "mcp__atilab__atilab_get_page",
      "mcp__atilab__atilab_get_published_results",
      "mcp__atilab__atilab_get_contact"
    ],
    "ask": [
      "mcp__atilab__atilab_send_enquiry"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as atilab. Review it before you use it.

Capability tags behind 4 rules
  • mcp__atilab__atilab_get_company_facts private-data
  • mcp__atilab__atilab_get_page untrusted-input
  • mcp__atilab__atilab_get_contact private-data
  • mcp__atilab__atilab_send_enquiry untrusted-input, outbound

Pin

Keep the decision: fail CI when the tools change, follow every change, or show a badge.

Pin in CI

Fail a build when the tools you reviewed are not the tools the server serves today.

curl -s "https://radar.anlyon.com/api/v1/servers/io.atilab/mcp/verify?hash=0ffdccfb3527cbbeac0c7e76d62610a908470f6a0618a3b26f1033858d825ff5" | jq -e '.changed == false'

Pinned hash 0ffdccfb3527, from Nov 15, 2026, 13:18 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/io.atilab/mcp/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for io.atilab/mcp
[![Anlyon Radar](https://radar.anlyon.com/badge/io.atilab/mcp.svg)](https://radar.anlyon.com/servers/io.atilab/mcp)

Source: MCP Registry. Synced Oct 21, 2026, 18:13 UTC.

ATI Lab MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the ATI Lab MCP server safe?

No scan can promise that. What its definitions show: 6 tools, 1 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the ATI Lab MCP server delete data?

No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.

Can the ATI Lab MCP server do things that cannot be undone?

Yes. 1 tool can send, pay, publish or merge: atilab_send_enquiry.

What tools does the ATI Lab MCP server have?

6 tools: 1 irreversible, 5 read. atilab_send_enquiry, atilab_get_company_facts, atilab_get_site_index, atilab_get_page, atilab_get_published_results and atilab_get_contact.

Does the ATI Lab MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the ATI Lab MCP server send data to outside services?

1 tool can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): atilab_send_enquiry.

Has the ATI Lab MCP server changed its tools?

Yes, once since Anlyon Radar started tracking it, most recently on Nov 2, 2026. Every change is on this page and in its Atom feed.